mirror of
https://github.com/ollama/ollama.git
synced 2026-11-08 02:16:57 -06:00
Jesse Gross
2e036e7cdf
The MLX runner is the only Go inference runner left and is no longer experimental, so its packages leave x/. The bindings become a top-level mlx package beside the carried patches in mlx/compat, mirroring how llama/ holds the llama.cpp integration, and the runner becomes mlxrunner with the architectures nested under the package they implement. Subpackages move with their parent unless listed. x/mlxrunner/mlx mlx x/internal/mlxthread mlx/mlxthread x/internal/mlxthreadtest mlx/mlxthread/mlxthreadtest x/internal/mlxtest mlx/mlxtest x/quant mlx/quant mlx/compat/*.patch mlx/compat/mlx-c (MLX patches go in mlx/compat/mlx) x/mlxrunner mlxrunner x/models/nn mlxrunner/nn x/models/<arch> mlxrunner/model/<arch> x/mlxrunner/imports.go mlxrunner/model/architectures (new package) x/create create x/safetensors fs/safetensors x/tokenizer mlxrunner/tokenizer Every package keeps its name, so the Go changes are the import path rewrites the moves force, and the CMake, Dockerfile, CI cache keys, drift check and Darwin payload script follow the new paths. Four edits are not paths: the runner's blank architecture imports become the package mlxrunner/model/architectures, so the list to extend for a new model sits beside the architecture directories; a depguard rule keeps the two test harnesses out of non-test code, as the x/internal placement used to; the CI change filter's two entries for the long-deleted x/imagegen/mlx now name the bindings' CMake project and the carried patches, so a change to either builds the payload; and the tokenizer parity test reads its fixtures from its own testdata instead of walking out of x/. x/server and x/imagegen/manifest stay for the next two commits.
95 lines
1.7 KiB
Go
95 lines
1.7 KiB
Go
package mlx
|
|
|
|
// #include "generated.h"
|
|
import "C"
|
|
|
|
type DType int
|
|
|
|
func (t DType) String() string {
|
|
switch t {
|
|
case DTypeBool:
|
|
return "BOOL"
|
|
case DTypeUint8:
|
|
return "U8"
|
|
case DTypeUint16:
|
|
return "U16"
|
|
case DTypeUint32:
|
|
return "U32"
|
|
case DTypeUint64:
|
|
return "U64"
|
|
case DTypeInt8:
|
|
return "I8"
|
|
case DTypeInt16:
|
|
return "I16"
|
|
case DTypeInt32:
|
|
return "I32"
|
|
case DTypeInt64:
|
|
return "I64"
|
|
case DTypeFloat16:
|
|
return "F16"
|
|
case DTypeFloat32:
|
|
return "F32"
|
|
case DTypeFloat64:
|
|
return "F64"
|
|
case DTypeBFloat16:
|
|
return "BF16"
|
|
case DTypeComplex64:
|
|
return "C64"
|
|
default:
|
|
return "Unknown"
|
|
}
|
|
}
|
|
|
|
func (t *DType) UnmarshalJSON(b []byte) error {
|
|
switch string(b) {
|
|
case `"BOOL"`:
|
|
*t = DTypeBool
|
|
case `"U8"`:
|
|
*t = DTypeUint8
|
|
case `"U16"`:
|
|
*t = DTypeUint16
|
|
case `"U32"`:
|
|
*t = DTypeUint32
|
|
case `"U64"`:
|
|
*t = DTypeUint64
|
|
case `"I8"`:
|
|
*t = DTypeInt8
|
|
case `"I16"`:
|
|
*t = DTypeInt16
|
|
case `"I32"`:
|
|
*t = DTypeInt32
|
|
case `"I64"`:
|
|
*t = DTypeInt64
|
|
case `"F16"`:
|
|
*t = DTypeFloat16
|
|
case `"F64"`:
|
|
*t = DTypeFloat64
|
|
case `"F32"`:
|
|
*t = DTypeFloat32
|
|
case `"BF16"`:
|
|
*t = DTypeBFloat16
|
|
case `"C64"`:
|
|
*t = DTypeComplex64
|
|
default:
|
|
return nil
|
|
}
|
|
return nil
|
|
}
|
|
|
|
const (
|
|
DTypeBool DType = C.MLX_BOOL
|
|
DTypeUint8 DType = C.MLX_UINT8
|
|
DTypeUint16 DType = C.MLX_UINT16
|
|
DTypeUint32 DType = C.MLX_UINT32
|
|
DTypeUint64 DType = C.MLX_UINT64
|
|
DTypeInt8 DType = C.MLX_INT8
|
|
DTypeInt16 DType = C.MLX_INT16
|
|
DTypeInt32 DType = C.MLX_INT32
|
|
DTypeInt64 DType = C.MLX_INT64
|
|
DTypeFloat16 DType = C.MLX_FLOAT16
|
|
DTypeFloat32 DType = C.MLX_FLOAT32
|
|
DTypeFloat64 DType = C.MLX_FLOAT64
|
|
DTypeBFloat16 DType = C.MLX_BFLOAT16
|
|
DTypeComplex64 DType = C.MLX_COMPLEX64
|
|
)
|